Digital characterization of movement to detect and monitor disorders

Abstract

Introduced here are techniques for digitally characterizing the movement of a subject in order to detect the presence of a disorder or monitor the progression of the disorder. More specifically, one or more angular features can be identified that define how certain part(s) of the human body move relative to other part(s) of the human body. These angular feature(s) can be used, for example, to affirmatively diagnose instances of a disorder, eliminate a disorder as the source of symptoms experienced by a subject, generate confidence scores that can be used to assist in diagnosing a subject, monitor disorder progression due to treatment or lack thereof, etc.

What is claimed is: 
     
       1. A non-transitory computer-readable medium with instructions stored thereon that, when executed by a processor, cause the processor to perform operations comprising:
 acquiring movement data generated by monitoring movement of multiple markers that are adapted for arrangement on a human body of a subject while the human body performs an activity; 
 identifying an angular feature defined by the multiple markers,
 wherein the multiple markers include (i) a marker that is representative of a pivot point and (ii) a pair of markers that represent ends of branches extending from the pivot point, and 
 wherein the angular feature is defined by a spatial relationship between the pair of markers with respect to the marker; 
 
 computing a first set of values of the angular feature during the performance of the activity by analyzing the movement data; and 
 detecting a presence of a disorder by:
 comparing the first set of values of the angular feature to an angular feature set that includes a second set of values of the angular feature,
 wherein the second set of values corresponds to a performance of the activity by a person other than the subject who is known to represent a confirmed case of the disorder, and 
 
 producing, based on said comparing, an output that indicates a likelihood that the human body is affected by the disorder. 
 
 
     
     
       2. The non-transitory computer-readable medium of  claim 1 , wherein the operations further comprise:
 generating a similarity measure that represents statistical similarity between the first set of values and the second set of values of the angular feature; and 
 rendering an affirmative diagnosis of the disorder responsive to a determination that the similarity measure exceeds a certain threshold. 
 
     
     
       3. The non-transitory computer-readable medium of  claim 1 , wherein the operations further comprise:
 generating a similarity measure that represents statistical similarity between the first set of values and the second set of values of the angular feature; and 
 rendering a negative diagnosis of the disorder responsive to a determination that the similar measure does not exceed a certain threshold. 
 
     
     
       4. The non-transitory computer-readable medium of  claim 1 , wherein the operations further comprise:
 retrieving historical values of the angular feature from a database,
 wherein the historical values correspond to at least one prior performance of the activity by the human body; 
 
 comparing the first set of values of the angular feature to the historical values of the angular feature; and 
 estimating a measure for disorder progression based on said comparing. 
 
     
     
       5. The non-transitory computer-readable medium of  claim 1 , wherein the operations further comprise:
 causing generation of a notification that specifies the likelihood that the human body is affected by the disorder. 
 
     
     
       6. The non-transitory computer-readable medium of  claim 5 , wherein the notification is presented to a medical professional responsible for overseeing treatment of the human body under examination. 
     
     
       7. The non-transitory computer-readable medium of  claim 1 , wherein the operations further comprise:
 storing the first set of values of the angular feature in a subject profile representing a historical record of angular feature values associated with performances of the activity by the human body over an interval of time. 
 
     
     
       8. The non-transitory computer-readable medium of  claim 1 , wherein a location of each marker of the multiple markers is periodically monitored while the human body performs the activity. 
     
     
       9. The non-transitory computer-readable medium of  claim 1 , wherein a location of each marker of the multiple markers is continually monitored while the human body performs the activity. 
     
     
       10. The non-transitory computer-readable medium of  claim 1 , wherein each marker of the multiple markers corresponds to a different predetermined location on the human body. 
     
     
       11. A method comprising:
 acquiring, by a processor, movement data generated by monitoring movement of multiple markers that are adapted for arrangement on a human body of a subject while the human body performs an activity; 
 identifying, by the processor, an angular feature defined by the multiple markers,
 wherein the multiple markers include (i) a marker that is representative of a pivot point and (ii) a pair of markers that represent ends of branches extending from the pivot point, and 
 wherein the angular feature is defined by a spatial relationship between the pair of markers with respect to the marker; 
 
 computing, by the processor, a first set of values of the angular feature during the performance of the activity by analyzing the movement data; 
 generating, by the processor, a similarity measure that represents statistical similarity between the first set of values of the angular feature and an angular feature set that includes a second set of values of the angular feature,
 wherein the second set of values corresponds to a performance of the activity by a person other than the subject who is known to represent a confirmed case of a disorder; and 
 
 determining, by the processor based on the similarity measure, whether to diagnose the human body as having the disorder. 
 
     
     
       12. The method of  claim 11 , wherein the human body is diagnosed as having the disorder responsive to a determination that the similarity measure exceeds a threshold. 
     
     
       13. The method of  claim 11 , wherein the angular feature is one of multiple angular features monitored by the processor, and wherein each of the multiple angular features is defined by a subset of the multiple markers. 
     
     
       14. The method of  claim 11 , further comprising:
 performing analysis of variance on the first set of values of the angular feature. 
 
     
     
       15. The method of  claim 14 , wherein the similarity measure is an F-statistic determined through analysis of variance, and wherein said determining is based on a comparison of the F-statistic to a threshold. 
     
     
       16. A computing device comprising:
 a memory that includes instructions for monitoring disorder progression over time by analyzing movement during motion capture sessions, 
 wherein the instructions, when executed by a processor, cause the processor to:
 acquire movement data generated in a first motion capture session by monitoring movement of multiple markers that are adapted for arrangement on a human body while the human body performs an activity; 
 compute values for an angular feature defined by the multiple markers during the performance of the activity based on locations of the multiple markers at corresponding points in time; 
 retrieve historical values of the angular feature from a database,
 wherein the historical values correspond to at least one prior performance of the activity by the human body in a second motion capture session; 
 
 estimate a measure for disorder progression based on a comparison of the values of the angular feature to the historical values of the angular feature; and 
 stratify the human body into a treatment program based on the measure for disorder progression. 
 
 
     
     
       17. The computing device of  claim 16 , wherein the instructions further cause the processor to:
 generate a similarity measure by comparing the values of the angular feature to an angular feature set known to represent at least one confirmed case of the disorder; and 
 render a diagnosis of the disorder based on the similarity measure. 
 
     
     
       18. The computing device of  claim 17 , wherein when the similarity measure exceeds a threshold, the diagnosis is an affirmative diagnosis of the disorder. 
     
     
       19. The computing device of  claim 17 , wherein the instructions further cause the processor to:
 generate a notification that specifies the diagnosis. 
 
     
     
       20. A non-transitory computer-readable medium with instructions stored thereon that, when executed by a processor, cause the processor to perform operations comprising:
 acquiring movement data that is generated by an inertial measurement unit that is located proximate to a first person while the first person performs an activity; 
 examining the movement data to infer movements of a first body part and a second body part with respect to a third body part,
 wherein a spatial relationship between the first and second body parts with respect to the third body part defines an angular feature; 
 
 computing a first set of values of the angular feature during the performance of the activity by analyzing the movement data; and 
 determining whether to diagnose the first person as having a disorder based on statistical similarity between the first set of values and a second set of values of the angular feature,
 wherein the second set of values corresponds to a performance of the activity by a second person who is known to represent a confirmed case of the disorder.